lm-swedish / tokenizer_config.json
birgermoell's picture
Initial commit
f185505
raw history blame
No virus
211 Bytes
{
"bos_token" : "<s>",
"do_lower_case" : true,
"eos_token" : "</s>",
"pad_token" : "<pad>",
"tokenizer_class" : "Wav2Vec2CTCTokenizer",
"unk_token" : "<unk>",
"word_delimiter_token" : "|"
}